Dissertation > Excellent graduate degree dissertation topics show
News Thread and Theme Detection
Author: LiFeng
Tutor: LiFang
School: Shanghai Jiaotong University
Course: Applied Computer Technology
Keywords: Event cued Cues and themes Topic Structure Mixed connection NMF Clustering
CLC: TP391.3
Type: Master's thesis
Year: 2008
Downloads: 146
Quote: 1
Read: Download Dissertation
Abstract
|
Network news has become the age of the Internet for people to obtain information , the main channel of the world . But as with the other network resources , there is the problem of information overload . The successful application of existing information retrieval - search engines , initially solved the users to quickly access the information they want . With a powerful search function , the user can quickly find the news events of concern . But for the impact of large , complex background events , news listed Organization ( news classification ) has been unable to meet the requirements of the age of the Internet it is quickly absorbed understand information . Automatically find the topic within the structure , to help users understand the grasp global overview of the event and the ins and outs , to sort out the internal logic of the event , and to become a current research focus . This paper topic structured , gives his own definition , that a topic of automatic organization consists of the following four points : a topic of a number of development clue ; theme of each development clues to the formation of multiple events ; topics and themes has a causal link and refinement of contact between the influence ( degrees) ; different themes . According to this definition , we are the first to use the clues to the topic named entity - based single-pass incremental clustering , clustering , we propose a hybrid join algorithm Unlike single connection and connection ; then we use each clue NMF clustering clues contained themes ; then based on similarity and whether the co-occurrence calculated the correlation of the theme ; the last news topic contains the number and the number of related topics , introduced the theme degrees . Used RSS news article online news publishing technologies and open source full-text search engine Lucene implemented a prototype system . And designed a series of experiments to verify the effectiveness of the two core clustering algorithm .
|
Related Dissertations
- Pyridine and a carboxylic acid ligand based supramolecular complexes,O621.13
- The neurolinguistics study of Chinese syntactic shift,H146
- The Analysis and Calculation of Steel Structural Connection,TU391
- The Practical Study of Research Course,G632.3
- A Study on the Application of Topical Structure Analysis as a Revision Strategy in Chinese College English Writing,H315
- Study on Chinese Topic Structure from Cognition-Based Semantic Approach,H13
- Analysis of Discourse Topic,H030
- The Research on Mixed Connection Verification Algorithm Against Denial of Service,TP393.08
- Topic Structure in Shaoyang Dialect,H17
- From the structural analysis of English majors topic mistakes in translation,H315.9
- "Ma Shi Wentong" the Language Searches with the Plane Micro,H13
- Coherence in English Reading Teaching,H319
- Double track railway under the deck arch bridge steel box frame Stress Analysis and Experimental Study,U441
- Catherine Ann Porter short stories explore the world of art,I712.074
- Structure of Lahu topic,H258
- Research on Topic Tracking and Evolution Analysis Technique,TP393.08
- Research on Intelligent Learning-Based Multi-Sensor Target Recognition and Tracking System,TP391.41
- Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
- The Discovery of User Concept Region Based on Multiple Instance Learning,TP391.41
- Feature Extraction, Selection and Combination in Lipreading,TP391.41
- Ontology -based Distributed Description Logic Modular Construction Methods,TP391.1
CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Retrieval machine
© 2012 www.DissertationTopic.Net Mobile
|